Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5916 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1833. Min Range: -5.1833

Max Act: 5.1833. Min Act: -0.0001

Data Index: 25686 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.9361. Min Act: -0.0000

Data Index: 706054 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.9698. Min Act: -0.0000

Data Index: 722891 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.9108. Min Act: -0.0000

Data Index: 1253746 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.8068. Min Act: -0.0000

Data Index: 1116725 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.6214. Min Act: -0.0000

Data Index: 42574 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.5539. Min Act: -0.0000

Data Index: 449831 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.5209. Min Act: -0.0000

Data Index: 425174 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.4930. Min Act: -0.0001

Data Index: 184227 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.1993. Min Act: -0.0000

Data Index: 151900 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.1731. Min Act: -0.0000

Data Index: 284556 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.2852. Min Act: -0.0000

Data Index: 97465 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.1028. Min Act: -0.0000

Data Index: 808276 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.2537. Min Act: -0.0000

Data Index: 336835 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.2719. Min Act: -0.0001

Data Index: 1021171 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.0793. Min Act: -0.0000

Data Index: 917906 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.2209. Min Act: -0.0000

Data Index: 259388 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.1658. Min Act: -0.0000

Data Index: 668335 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.1396. Min Act: -0.0000

Data Index: 701728 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 5.1833. Min Range: -5.1833

Max Act: 4.0761. Min Act: -0.0000

Data Index: 1218513 (C4 (Web Text))

Max Activating Token Index: 769